Merge remote-tracking branch 'origin/released'

Conflicts:
	libX11/configure.ac
	mesalib/src/mesa/main/ff_fragment_shader.cpp
	mesalib/src/mesa/main/framebuffer.c
	mesalib/src/mesa/main/texparam.c
	pixman/pixman/pixman-arm-neon-asm.S

13 files changed, 722 insertions, 720 deletions

diff --git a/libX11/configure.ac b/libX11/configure.ac
index 60a7790d8..e842bf3ec 100644
--- a/libX11/configure.ac
+++ b/libX11/configure.ac
@@ -1,7 +1,7 @@
 

 # Initialize Autoconf

 AC_PREREQ([2.60])

-AC_INIT([libX11], [1.4.3],

+AC_INIT([libX11], [1.4.4],

         [https://bugs.freedesktop.org/enter_bug.cgi?product=xorg], [libX11])

 AC_CONFIG_SRCDIR([Makefile.am])

 AC_CONFIG_HEADERS([src/config.h include/X11/XlibConf.h])

diff --git a/mesalib/configure.ac b/mesalib/configure.ac
index 5c832e646..1b1823a21 100644
--- a/mesalib/configure.ac
+++ b/mesalib/configure.ac
@@ -951,7 +951,7 @@ xyesyes)
         GL_PC_LIB_PRIV="$GL_LIB_DEPS"
         GL_PC_CFLAGS="$X11_INCLUDES"
     fi
-    GL_LIB_DEPS="$GL_LIB_DEPS $SELINUX_LIBS -lm -lpthread"
+    GL_LIB_DEPS="$GL_LIB_DEPS $SELINUX_LIBS -lm -lpthread $DLOPEN_LIBS"
     GL_PC_LIB_PRIV="$GL_PC_LIB_PRIV $SELINUX_LIBS -lm -lpthread"
 
     # if static, move the external libraries to the programs
@@ -1936,11 +1936,12 @@ if test "x$with_gallium_drivers" != x; then
             gallium_check_st "nouveau/drm" "dri-nouveau" "xorg-nouveau" "" "xvmc-nouveau"
             ;;
         xswrast)
+            GALLIUM_DRIVERS_DIRS="$GALLIUM_DRIVERS_DIRS softpipe"
+            if test "x$MESA_LLVM" = x1; then
+                GALLIUM_DRIVERS_DIRS="$GALLIUM_DRIVERS_DIRS llvmpipe"
+            fi
+
             if test "x$HAVE_ST_DRI" = xyes; then
-                GALLIUM_DRIVERS_DIRS="$GALLIUM_DRIVERS_DIRS softpipe"
-                if test "x$MESA_LLVM" = x1; then
-                    GALLIUM_DRIVERS_DIRS="$GALLIUM_DRIVERS_DIRS llvmpipe"
-                fi
                 GALLIUM_TARGET_DIRS="$GALLIUM_TARGET_DIRS dri-swrast"
             fi
             if test "x$HAVE_ST_VDPAU" = xyes; then
@@ -1958,9 +1959,6 @@ if test "x$with_gallium_drivers" != x; then
                if test "x$HAVE_WINSYS_XLIB" != xyes; then
                   GALLIUM_WINSYS_DIRS="$GALLIUM_WINSYS_DIRS sw/xlib"
                fi
-               if test "x$HAVE_ST_DRI" != xyes; then
-                GALLIUM_DRIVERS_DIRS="$GALLIUM_DRIVERS_DIRS softpipe"
-               fi
             fi
             ;;
         *)
diff --git a/mesalib/src/glsl/Makefile b/mesalib/src/glsl/Makefile
index 005b51d72..c20a6c9ed 100644
--- a/mesalib/src/glsl/Makefile
+++ b/mesalib/src/glsl/Makefile
@@ -164,6 +164,7 @@ depend: $(ALL_SOURCES) Makefile
 	rm -f depend
 	touch depend
 	$(MKDEP) $(MKDEP_OPTIONS) $(INCLUDES) $(ALL_SOURCES) 2> /dev/null
+	$(MKDEP) $(MKDEP_OPTIONS) -a -p $(DRICORE_OBJ_DIR)/ $(INCLUDES) $(ALL_SOURCES) 2> /dev/null
 
 # Remove .o and backup files
 clean: clean-dricore
diff --git a/mesalib/src/glsl/TODO b/mesalib/src/glsl/TODO
index 6eed986bf..c99d7e152 100644
--- a/mesalib/src/glsl/TODO
+++ b/mesalib/src/glsl/TODO
@@ -1,38 +1,27 @@
-- Detect code paths in non-void functions that don't reach a return statement

-

-- Improve handling of constants and their initializers.  Constant initializers

-  should never generate any code.  This is trival for scalar constants.  It is

-  also trivial for arrays, matrices, and vectors that are accessed with

-  constant index values.  For others it is more complicated.  Perhaps these

-  cases should be silently converted to uniforms?

-

-- Implement support for ir_binop_dot in ir_algebraic.cpp.  Perform

-  transformations such as "dot(v, vec3(0.0, 1.0, 0.0))" -> v.y.

-

-1.30 features:

-

-- Implement AST-to-HIR conversion of bit-shift operators.

-

-- Implement AST-to-HIR conversion of bit-wise {&,|,^,!} operators.

-

-- Implement AST-to-HIR conversion of switch-statements

-  - switch

-  - case

-  - Update break to correcly handle mixed nexting of switch-statements

-    and loops.

-

-- Handle currently unsupported constant expression types

-  - ir_unop_bit_not

-  - ir_binop_mod

-  - ir_binop_lshift

-  - ir_binop_rshift

-  - ir_binop_bit_and

-  - ir_binop_bit_xor

-  - ir_binop_bit_or

-

-- Implement support for 1.30 style shadow compares which only return a float

-  instead of a vec4.

-

-- Implement support for gl_ClipDistance.  This is non-trivial because

-  gl_ClipDistance is exposed as a float[8], but all hardware actually

+- Detect code paths in non-void functions that don't reach a return statement
+
+- Improve handling of constants and their initializers.  Constant initializers
+  should never generate any code.  This is trival for scalar constants.  It is
+  also trivial for arrays, matrices, and vectors that are accessed with
+  constant index values.  For others it is more complicated.  Perhaps these
+  cases should be silently converted to uniforms?
+
+- Implement support for ir_binop_dot in ir_algebraic.cpp.  Perform
+  transformations such as "dot(v, vec3(0.0, 1.0, 0.0))" -> v.y.
+
+- Track source locations throughout the IR.  There are currently several
+  places where we cannot emit line numbers for errors (and currently emit 0:0)
+  because we've "lost" the line number information.  This is particularly
+  noticeable at link time.
+
+1.30 features:
+
+- Implement AST-to-HIR conversion of switch-statements
+  - switch
+  - case
+  - Update break to correcly handle mixed nexting of switch-statements
+    and loops.
+
+- Implement support for gl_ClipDistance.  This is non-trivial because
+  gl_ClipDistance is exposed as a float[8], but all hardware actually
   implements it as vec4[2].
\ No newline at end of file
diff --git a/mesalib/src/mesa/Makefile b/mesalib/src/mesa/Makefile
index e17ee3b58..88f31b686 100644
--- a/mesalib/src/mesa/Makefile
+++ b/mesalib/src/mesa/Makefile
@@ -1,230 +1,231 @@
-# src/mesa/Makefile

-

-TOP = ../..

-include $(TOP)/configs/current

-

-MESA_LIBS := libmesa.a libmesagallium.a

-DEPENDS := depend

-

-MESA_OBJ_DIR := .

-DRICORE_OBJ_DIR := objs-dricore

-

-include sources.mak

-

-# adjust object dirs

-MESA_OBJECTS := $(addprefix $(MESA_OBJ_DIR)/, $(MESA_OBJECTS))

-MESA_GALLIUM_OBJECTS := $(addprefix $(MESA_OBJ_DIR)/, $(MESA_GALLIUM_OBJECTS))

-

-DRICORE_OBJECTS := $(addprefix $(DRICORE_OBJ_DIR)/, $(MESA_OBJECTS))

-

-# define preprocessor flags

-MESA_CPPFLAGS := $(API_DEFINES) $(DEFINES)

-

-# append include dirs

-MESA_CPPFLAGS += $(INCLUDE_DIRS)

-

-DRICORE_CPPFLAGS = $(MESA_CPPFLAGS)

-

-# tidy compiler flags

-CFLAGS := $(filter-out $(DEFINES), $(CFLAGS))

-CXXFLAGS := $(filter-out $(DEFINES), $(CXXFLAGS))

-

-# LLVM is needed for the state tracker

-MESA_CFLAGS := $(LLVM_CFLAGS) $(CFLAGS)

-DRICORE_CFLAGS := $(LLVM_CFLAGS) $(DRI_CFLAGS)

-

-MESA_CXXFLAGS := $(LLVM_CFLAGS) $(CXXFLAGS)

-DRICORE_CXXFLAGS := $(LLVM_CFLAGS) $(DRI_CXXFLAGS)

-

-define mesa-cc-c

-	@mkdir -p $(dir $@)

-	$(CC) -c -o $@ $< $($(1)_CPPFLAGS) $($(1)_CFLAGS)

-endef

-

-define mesa-cxx-c

-	@mkdir -p $(dir $@)

-	$(CXX) -c -o $@ $< $($(1)_CPPFLAGS) $($(1)_CXXFLAGS)

-endef

-

-$(MESA_OBJ_DIR)/%.o: %.c

-	$(call mesa-cc-c,MESA)

-

-$(MESA_OBJ_DIR)/%.o: %.cpp

-	$(call mesa-cxx-c,MESA)

-

-$(MESA_OBJ_DIR)/%.o: %.S

-	$(call mesa-cc-c,MESA)

-

-$(DRICORE_OBJ_DIR)/%.o: %.c

-	$(call mesa-cc-c,DRICORE)

-

-$(DRICORE_OBJ_DIR)/%.o: %.cpp

-	$(call mesa-cxx-c,DRICORE)

-

-$(DRICORE_OBJ_DIR)/%.o: %.S

-	$(call mesa-cc-c,DRICORE)

-

-# Default: build dependencies, then asm_subdirs, GLSL built-in lib,

-# then convenience libs (.a) and finally the device drivers:

-default: $(DEPENDS) asm_subdirs $(MESA_LIBS) $(DRICORE_LIBS) driver_subdirs

-

-main/api_exec_es1.c: main/APIspec.xml main/es_generator.py main/APIspecutil.py main/APIspec.py

-	$(PYTHON2) $(PYTHON_FLAGS) main/es_generator.py -S main/APIspec.xml -V GLES1.1 > $@

-

-main/api_exec_es2.c: main/APIspec.xml main/es_generator.py main/APIspecutil.py main/APIspec.py

-	$(PYTHON2) $(PYTHON_FLAGS) main/es_generator.py -S main/APIspec.xml -V GLES2.0 > $@

-

-program/program_parse.tab.c program/program_parse.tab.h: program/program_parse.y

-	$(BISON) -v -d --output=program/program_parse.tab.c $<

-

-program/lex.yy.c: program/program_lexer.l

-	$(FLEX) --never-interactive --outfile=$@ $<

-

-######################################################################

-# Helper libraries used by many drivers:

-

-# Make archive of core mesa object files

-libmesa.a: $(MESA_OBJECTS) $(GLSL_LIBS)

-	@ $(MKLIB) -o mesa -static $(MESA_OBJECTS) $(GLSL_LIBS)

-

-# Shared dricore library for classic DRI drivers

-$(TOP)/$(LIB_DIR)/libdricore.so: $(DRICORE_OBJECTS) $(DRICORE_GLSL_LIBS)

-	@$(MKLIB) -o $@ -linker '$(CXX)' -ldflags '$(LDFLAGS)' \

-		-cplusplus -noprefix \

-		-install $(TOP)/$(LIB_DIR) -id $(DRI_DRIVER_INSTALL_DIR)/$@.dylib \

-		$(DRICORE_LIB_DEPS) $(DRICORE_OBJECTS)

-

-# Make archive of subset of core mesa object files for gallium

-libmesagallium.a: $(MESA_GALLIUM_OBJECTS) $(GLSL_LIBS)

-	@ $(MKLIB) -o mesagallium -static $(MESA_GALLIUM_OBJECTS) $(GLSL_LIBS)

-

-######################################################################

-# Device drivers

-driver_subdirs: $(MESA_LIBS) $(DRICORE_LIBS)

-	@ (cd drivers && $(MAKE))

-

-

-######################################################################

-# Assembly subdirs

-asm_subdirs:

-	@ if echo "$(ASM_FLAGS)" | grep -q USE_X86_ASM ; then \

-		(cd x86 && $(MAKE)) || exit 1 ; \

-	fi

-	@ if echo "$(ASM_FLAGS)" | grep -q USE_X86_64_ASM ; then \

-		(cd x86 && $(MAKE)) || exit 1 ; \

-		(cd x86-64 && $(MAKE)) || exit 1 ; \

-	fi

-

-

-######################################################################

-# Dependency generation

-

-depend: $(ALL_SOURCES)

-	@ echo "running $(MKDEP)"

-	@ touch depend

-	@$(MKDEP) $(MKDEP_OPTIONS) -p$(MESA_OBJ_DIR)/ $(MESA_CPPFLAGS) \

-		$(ALL_SOURCES) > /dev/null 2>/dev/null

-

-######################################################################

-# Installation rules

-

-# this isn't fleshed out yet but is probably the way to go in the future

-new_install:

-	(cd drivers && $(MAKE) install)

-

-ifneq (,$(DRICORE_LIBS))

-DRICORE_INSTALL_TARGET = install-dricore

-endif

-

-# XXX replace this with new_install above someday

-install: default $(DRICORE_INSTALL_TARGET)

-	@for driver in $(DRIVER_DIRS) ; do \

-	  case "$$driver" in \

-	    osmesa) if [ "$(DRIVER_DIRS)" = osmesa ]; then \

-	              $(MAKE) install-headers install-osmesa || exit 1 ; \

-	            else \

-	              $(MAKE) install-osmesa || exit 1 ; \

-	            fi ;; \

-	    dri)    $(MAKE) install-libgl install-dri || exit 1 ;; \

-	    *)      $(MAKE) install-libgl || exit 1 ;; \

-	  esac ; \

-	done

-

-pcedit = \

-	-e 's,@INSTALL_DIR@,$(INSTALL_DIR),' \

-	-e 's,@INSTALL_LIB_DIR@,$(INSTALL_LIB_DIR),' \

-	-e 's,@INSTALL_INC_DIR@,$(INSTALL_INC_DIR),' \

-	-e 's,@VERSION@,$(MESA_MAJOR).$(MESA_MINOR).$(MESA_TINY),' \

-

-

-gl_pcedit = sed \

-	$(pcedit) \

-	-e 's,@GL_PC_REQ_PRIV@,$(GL_PC_REQ_PRIV),' \

-	-e 's,@GL_PC_LIB_PRIV@,$(GL_PC_LIB_PRIV),' \

-	-e 's,@GL_PC_CFLAGS@,$(GL_PC_CFLAGS),' \

-	-e 's,@GLX_TLS@,$(GLX_TLS),' \

-	-e 's,@GL_LIB@,$(GL_LIB),'

-

-gl.pc: gl.pc.in

-	$(gl_pcedit) $< > $@

-

-osmesa_pcedit = sed \

-	$(pcedit) \

-	-e 's,@OSMESA_LIB@,$(OSMESA_LIB),' \

-	-e 's,@OSMESA_PC_REQ@,$(OSMESA_PC_REQ),' \

-	-e 's,@OSMESA_PC_LIB_PRIV@,$(OSMESA_PC_LIB_PRIV),'

-

-osmesa.pc: osmesa.pc.in

-	$(osmesa_pcedit) $< > $@

-

-install-headers:

-	$(INSTALL) -d $(DESTDIR)$(INSTALL_INC_DIR)/GL

-	$(INSTALL) -m 644 $(TOP)/include/GL/*.h \

-		$(DESTDIR)$(INSTALL_INC_DIR)/GL

-

-install-libgl: default gl.pc install-headers

-	$(INSTALL) -d $(DESTDIR)$(INSTALL_LIB_DIR)

-	$(INSTALL) -d $(DESTDIR)$(INSTALL_LIB_DIR)/pkgconfig

-	$(MINSTALL) $(TOP)/$(LIB_DIR)/$(GL_LIB_GLOB) \

-		$(DESTDIR)$(INSTALL_LIB_DIR)

-	$(INSTALL) -m 644 gl.pc $(DESTDIR)$(INSTALL_LIB_DIR)/pkgconfig

-

-install-osmesa: default osmesa.pc

-	$(INSTALL) -d $(DESTDIR)$(INSTALL_LIB_DIR)

-	$(INSTALL) -d $(DESTDIR)$(INSTALL_LIB_DIR)/pkgconfig

-	$(MINSTALL) $(TOP)/$(LIB_DIR)/$(OSMESA_LIB_GLOB) \

-		$(DESTDIR)$(INSTALL_LIB_DIR)

-	$(INSTALL) -m 644 osmesa.pc $(DESTDIR)$(INSTALL_LIB_DIR)/pkgconfig

-

-install-dri: default

-	cd drivers/dri && $(MAKE) install

-

-# We don't need MINSTALL here because we're not installing symbolic links

-install-dricore: default

-	$(INSTALL) -d $(DESTDIR)$(DRI_DRIVER_INSTALL_DIR)

-	$(INSTALL) -m 755 $(DRICORE_LIBS) $(DESTDIR)$(DRI_DRIVER_INSTALL_DIR)

-

-

-# Emacs tags

-tags:

-	etags `find . -name \*.[ch]` $(TOP)/include/GL/*.h

-

-clean-dricore:

-	-rm -f libdricore.so

-	-rm -f $(DRICORE_LIBS)

-	-rm -rf $(DRICORE_OBJ_DIR)

-

-clean: clean-dricore

-	-rm -f */*.o

-	-rm -f */*/*.o

-	-rm -f depend depend.bak libmesa.a libmesagallium.a

-	-rm -f drivers/*/*.o

-	-rm -f *.pc

-	-@cd drivers/dri && $(MAKE) clean

-	-@cd drivers/x11 && $(MAKE) clean

-	-@cd drivers/osmesa && $(MAKE) clean

-	-@cd x86 && $(MAKE) clean

-	-@cd x86-64 && $(MAKE) clean

-

-

--include $(DEPENDS)

+# src/mesa/Makefile
+
+TOP = ../..
+include $(TOP)/configs/current
+
+MESA_LIBS := libmesa.a libmesagallium.a
+DEPENDS := depend
+
+MESA_OBJ_DIR := .
+DRICORE_OBJ_DIR := objs-dricore
+
+include sources.mak
+
+# adjust object dirs
+DRICORE_OBJECTS := $(addprefix $(DRICORE_OBJ_DIR)/, $(MESA_OBJECTS))
+MESA_OBJECTS := $(addprefix $(MESA_OBJ_DIR)/, $(MESA_OBJECTS))
+MESA_GALLIUM_OBJECTS := $(addprefix $(MESA_OBJ_DIR)/, $(MESA_GALLIUM_OBJECTS))
+
+# define preprocessor flags
+MESA_CPPFLAGS := $(API_DEFINES) $(DEFINES)
+
+# append include dirs
+MESA_CPPFLAGS += $(INCLUDE_DIRS)
+
+DRICORE_CPPFLAGS = $(MESA_CPPFLAGS)
+
+# tidy compiler flags
+CFLAGS := $(filter-out $(DEFINES), $(CFLAGS))
+CXXFLAGS := $(filter-out $(DEFINES), $(CXXFLAGS))
+
+# LLVM is needed for the state tracker
+MESA_CFLAGS := $(LLVM_CFLAGS) $(CFLAGS)
+DRICORE_CFLAGS := $(LLVM_CFLAGS) $(DRI_CFLAGS)
+
+MESA_CXXFLAGS := $(LLVM_CFLAGS) $(CXXFLAGS)
+DRICORE_CXXFLAGS := $(LLVM_CFLAGS) $(DRI_CXXFLAGS)
+
+define mesa-cc-c
+	@mkdir -p $(dir $@)
+	$(CC) -c -o $@ $< $($(1)_CPPFLAGS) $($(1)_CFLAGS)
+endef
+
+define mesa-cxx-c
+	@mkdir -p $(dir $@)
+	$(CXX) -c -o $@ $< $($(1)_CPPFLAGS) $($(1)_CXXFLAGS)
+endef
+
+$(MESA_OBJ_DIR)/%.o: %.c
+	$(call mesa-cc-c,MESA)
+
+$(MESA_OBJ_DIR)/%.o: %.cpp
+	$(call mesa-cxx-c,MESA)
+
+$(MESA_OBJ_DIR)/%.o: %.S
+	$(call mesa-cc-c,MESA)
+
+$(DRICORE_OBJ_DIR)/%.o: %.c
+	$(call mesa-cc-c,DRICORE)
+
+$(DRICORE_OBJ_DIR)/%.o: %.cpp
+	$(call mesa-cxx-c,DRICORE)
+
+$(DRICORE_OBJ_DIR)/%.o: %.S
+	$(call mesa-cc-c,DRICORE)
+
+# Default: build dependencies, then asm_subdirs, GLSL built-in lib,
+# then convenience libs (.a) and finally the device drivers:
+default: $(DEPENDS) asm_subdirs $(MESA_LIBS) $(DRICORE_LIBS) driver_subdirs
+
+main/api_exec_es1.c: main/APIspec.xml main/es_generator.py main/APIspecutil.py main/APIspec.py
+	$(PYTHON2) $(PYTHON_FLAGS) main/es_generator.py -S main/APIspec.xml -V GLES1.1 > $@
+
+main/api_exec_es2.c: main/APIspec.xml main/es_generator.py main/APIspecutil.py main/APIspec.py
+	$(PYTHON2) $(PYTHON_FLAGS) main/es_generator.py -S main/APIspec.xml -V GLES2.0 > $@
+
+program/program_parse.tab.c program/program_parse.tab.h: program/program_parse.y
+	$(BISON) -v -d --output=program/program_parse.tab.c $<
+
+program/lex.yy.c: program/program_lexer.l
+	$(FLEX) --never-interactive --outfile=$@ $<
+
+######################################################################
+# Helper libraries used by many drivers:
+
+# Make archive of core mesa object files
+libmesa.a: $(MESA_OBJECTS) $(GLSL_LIBS)
+	@ $(MKLIB) -o mesa -static $(MESA_OBJECTS) $(GLSL_LIBS)
+
+# Shared dricore library for classic DRI drivers
+$(TOP)/$(LIB_DIR)/libdricore.so: $(DRICORE_OBJECTS) $(DRICORE_GLSL_LIBS)
+	@$(MKLIB) -o $@ -linker '$(CXX)' -ldflags '$(LDFLAGS)' \
+		-cplusplus -noprefix \
+		-install $(TOP)/$(LIB_DIR) -id $(DRI_DRIVER_INSTALL_DIR)/$@.dylib \
+		$(DRICORE_LIB_DEPS) $(DRICORE_OBJECTS)
+
+# Make archive of subset of core mesa object files for gallium
+libmesagallium.a: $(MESA_GALLIUM_OBJECTS) $(GLSL_LIBS)
+	@ $(MKLIB) -o mesagallium -static $(MESA_GALLIUM_OBJECTS) $(GLSL_LIBS)
+
+######################################################################
+# Device drivers
+driver_subdirs: $(MESA_LIBS) $(DRICORE_LIBS)
+	@ (cd drivers && $(MAKE))
+
+
+######################################################################
+# Assembly subdirs
+asm_subdirs:
+	@ if echo "$(ASM_FLAGS)" | grep -q USE_X86_ASM ; then \
+		(cd x86 && $(MAKE)) || exit 1 ; \
+	fi
+	@ if echo "$(ASM_FLAGS)" | grep -q USE_X86_64_ASM ; then \
+		(cd x86 && $(MAKE)) || exit 1 ; \
+		(cd x86-64 && $(MAKE)) || exit 1 ; \
+	fi
+
+
+######################################################################
+# Dependency generation
+
+depend: $(ALL_SOURCES)
+	@ echo "running $(MKDEP)"
+	@ touch depend
+	@$(MKDEP) $(MKDEP_OPTIONS) -p$(MESA_OBJ_DIR)/ $(MESA_CPPFLAGS) \
+		$(ALL_SOURCES) > /dev/null 2>/dev/null
+	@$(MKDEP) $(MKDEP_OPTIONS) -a -p$(DRICORE_OBJ_DIR)/ $(MESA_CPPFLAGS) \
+		$(ALL_SOURCES) > /dev/null 2>/dev/null
+
+######################################################################
+# Installation rules
+
+# this isn't fleshed out yet but is probably the way to go in the future
+new_install:
+	(cd drivers && $(MAKE) install)
+
+ifneq (,$(DRICORE_LIBS))
+DRICORE_INSTALL_TARGET = install-dricore
+endif
+
+# XXX replace this with new_install above someday
+install: default $(DRICORE_INSTALL_TARGET)
+	@for driver in $(DRIVER_DIRS) ; do \
+	  case "$$driver" in \
+	    osmesa) if [ "$(DRIVER_DIRS)" = osmesa ]; then \
+	              $(MAKE) install-headers install-osmesa || exit 1 ; \
+	            else \
+	              $(MAKE) install-osmesa || exit 1 ; \
+	            fi ;; \
+	    dri)    $(MAKE) install-libgl install-dri || exit 1 ;; \
+	    *)      $(MAKE) install-libgl || exit 1 ;; \
+	  esac ; \
+	done
+
+pcedit = \
+	-e 's,@INSTALL_DIR@,$(INSTALL_DIR),' \
+	-e 's,@INSTALL_LIB_DIR@,$(INSTALL_LIB_DIR),' \
+	-e 's,@INSTALL_INC_DIR@,$(INSTALL_INC_DIR),' \
+	-e 's,@VERSION@,$(MESA_MAJOR).$(MESA_MINOR).$(MESA_TINY),' \
+
+
+gl_pcedit = sed \
+	$(pcedit) \
+	-e 's,@GL_PC_REQ_PRIV@,$(GL_PC_REQ_PRIV),' \
+	-e 's,@GL_PC_LIB_PRIV@,$(GL_PC_LIB_PRIV),' \
+	-e 's,@GL_PC_CFLAGS@,$(GL_PC_CFLAGS),' \
+	-e 's,@GLX_TLS@,$(GLX_TLS),' \
+	-e 's,@GL_LIB@,$(GL_LIB),'
+
+gl.pc: gl.pc.in
+	$(gl_pcedit) $< > $@
+
+osmesa_pcedit = sed \
+	$(pcedit) \
+	-e 's,@OSMESA_LIB@,$(OSMESA_LIB),' \
+	-e 's,@OSMESA_PC_REQ@,$(OSMESA_PC_REQ),' \
+	-e 's,@OSMESA_PC_LIB_PRIV@,$(OSMESA_PC_LIB_PRIV),'
+
+osmesa.pc: osmesa.pc.in
+	$(osmesa_pcedit) $< > $@
+
+install-headers:
+	$(INSTALL) -d $(DESTDIR)$(INSTALL_INC_DIR)/GL
+	$(INSTALL) -m 644 $(TOP)/include/GL/*.h \
+		$(DESTDIR)$(INSTALL_INC_DIR)/GL
+
+install-libgl: default gl.pc install-headers
+	$(INSTALL) -d $(DESTDIR)$(INSTALL_LIB_DIR)
+	$(INSTALL) -d $(DESTDIR)$(INSTALL_LIB_DIR)/pkgconfig
+	$(MINSTALL) $(TOP)/$(LIB_DIR)/$(GL_LIB_GLOB) \
+		$(DESTDIR)$(INSTALL_LIB_DIR)
+	$(INSTALL) -m 644 gl.pc $(DESTDIR)$(INSTALL_LIB_DIR)/pkgconfig
+
+install-osmesa: default osmesa.pc
+	$(INSTALL) -d $(DESTDIR)$(INSTALL_LIB_DIR)
+	$(INSTALL) -d $(DESTDIR)$(INSTALL_LIB_DIR)/pkgconfig
+	$(MINSTALL) $(TOP)/$(LIB_DIR)/$(OSMESA_LIB_GLOB) \
+		$(DESTDIR)$(INSTALL_LIB_DIR)
+	$(INSTALL) -m 644 osmesa.pc $(DESTDIR)$(INSTALL_LIB_DIR)/pkgconfig
+
+install-dri: default
+	cd drivers/dri && $(MAKE) install
+
+# We don't need MINSTALL here because we're not installing symbolic links
+install-dricore: default
+	$(INSTALL) -d $(DESTDIR)$(DRI_DRIVER_INSTALL_DIR)
+	$(INSTALL) -m 755 $(DRICORE_LIBS) $(DESTDIR)$(DRI_DRIVER_INSTALL_DIR)
+
+
+# Emacs tags
+tags:
+	etags `find . -name \*.[ch]` $(TOP)/include/GL/*.h
+
+clean-dricore:
+	-rm -f libdricore.so
+	-rm -f $(DRICORE_LIBS)
+	-rm -rf $(DRICORE_OBJ_DIR)
+
+clean: clean-dricore
+	-rm -f */*.o
+	-rm -f */*/*.o
+	-rm -f depend depend.bak libmesa.a libmesagallium.a
+	-rm -f drivers/*/*.o
+	-rm -f *.pc
+	-@cd drivers/dri && $(MAKE) clean
+	-@cd drivers/x11 && $(MAKE) clean
+	-@cd drivers/osmesa && $(MAKE) clean
+	-@cd x86 && $(MAKE) clean
+	-@cd x86-64 && $(MAKE) clean
+
+
+-include $(DEPENDS)
diff --git a/mesalib/src/mesa/drivers/common/meta.c b/mesalib/src/mesa/drivers/common/meta.c
index 26c895196..f9b475598 100644
--- a/mesalib/src/mesa/drivers/common/meta.c
+++ b/mesalib/src/mesa/drivers/common/meta.c
@@ -2869,6 +2869,16 @@ copy_tex_sub_image(struct gl_context *ctx,
 
    /* Choose format/type for temporary image buffer */
    format = _mesa_get_format_base_format(texImage->TexFormat);
+   if (format == GL_LUMINANCE ||
+       format == GL_LUMINANCE_ALPHA ||
+       format == GL_INTENSITY) {
+      /* We don't want to use GL_LUMINANCE, GL_INTENSITY, etc. for the
+       * temp image buffer because glReadPixels will do L=R+G+B which is
+       * not what we want (should be L=R).
+       */
+      format = GL_RGBA;
+   }
+
    type = get_temp_image_type(ctx, format);
    bpp = _mesa_bytes_per_pixel(format, type);
    if (bpp <= 0) {
diff --git a/mesalib/src/mesa/main/ff_fragment_shader.cpp b/mesalib/src/mesa/main/ff_fragment_shader.cpp
index 562a37b81..28032b1a0 100644
--- a/mesalib/src/mesa/main/ff_fragment_shader.cpp
+++ b/mesalib/src/mesa/main/ff_fragment_shader.cpp
@@ -330,8 +330,7 @@ static GLbitfield get_fp_input_mask( struct gl_context *ctx )
       /* _NEW_RENDERMODE */

       fp_inputs = (FRAG_BIT_COL0 | FRAG_BIT_TEX0);

    }

-   else if (!(vertexProgram || vertexShader) ||

-            !ctx->VertexProgram._Current) {

+   else if (!(vertexProgram || vertexShader)) {

       /* Fixed function vertex logic */

       /* _NEW_ARRAY */

       GLbitfield varying_inputs = ctx->varying_vp_inputs;

diff --git a/mesalib/src/mesa/main/framebuffer.c b/mesalib/src/mesa/main/framebuffer.c
index a32976211..fd499ab2b 100644
--- a/mesalib/src/mesa/main/framebuffer.c
+++ b/mesalib/src/mesa/main/framebuffer.c
@@ -548,6 +548,7 @@ _mesa_update_framebuffer_visual(struct gl_context *ctx,
             fb->Visual.rgbBits = fb->Visual.redBits

                + fb->Visual.greenBits + fb->Visual.blueBits;

             fb->Visual.samples = rb->NumSamples;

+            fb->Visual.sampleBuffers = rb->NumSamples > 0 ? 1 : 0;

             if (_mesa_get_format_color_encoding(fmt) == GL_SRGB)

                 fb->Visual.sRGBCapable = ctx->Const.sRGBCapable;

             break;

diff --git a/mesalib/src/mesa/main/texparam.c b/mesalib/src/mesa/main/texparam.c
index f62745770..1e51782d7 100644
--- a/mesalib/src/mesa/main/texparam.c
+++ b/mesalib/src/mesa/main/texparam.c
@@ -888,7 +888,7 @@ _mesa_GetTexLevelParameteriv( GLenum target, GLint level,
    texObj = _mesa_select_tex_object(ctx, texUnit, target);

 

    img = _mesa_select_tex_image(ctx, texObj, target, level);

-   if (!img || !img->TexFormat) {

+   if (!img || img->TexFormat == MESA_FORMAT_NONE) {

       /* undefined texture image */

       if (pname == GL_TEXTURE_COMPONENTS)

          *params = 1;

diff --git a/mesalib/src/mesa/state_tracker/st_atom_texture.c b/mesalib/src/mesa/state_tracker/st_atom_texture.c
index 800a9f1f0..3115a2511 100644
--- a/mesalib/src/mesa/state_tracker/st_atom_texture.c
+++ b/mesalib/src/mesa/state_tracker/st_atom_texture.c
@@ -221,9 +221,9 @@ update_single_texture(struct st_context *st, struct pipe_sampler_view **sampler_
 
       if ((samp->sRGBDecode == GL_SKIP_DECODE_EXT) &&
 	  (_mesa_get_format_color_encoding(texFormat) == GL_SRGB)) {
-	 /* don't do sRGB->RGB conversion.  Interpret the texture
-	  * texture data as linear values.
-	  */
+         /* Don't do sRGB->RGB conversion.  Interpret the texture data as
+          * linear values.
+          */
 	 const gl_format linearFormat =
 	    _mesa_get_srgb_format_linear(texFormat);
 	 firstImageFormat = st_mesa_format_to_pipe_format(linearFormat);
diff --git a/pixman/pixman/pixman-arm-neon-asm-bilinear.S b/pixman/pixman/pixman-arm-neon-asm-bilinear.S
index 9a4a1ffba..3c7fe0fea 100644
--- a/pixman/pixman/pixman-arm-neon-asm-bilinear.S
+++ b/pixman/pixman/pixman-arm-neon-asm-bilinear.S
@@ -66,6 +66,7 @@
 .eabi_attribute 12, 0
 .arm
 .altmacro
+.p2align 2
 
 #include "pixman-arm-neon-asm.h"
 
diff --git a/pixman/pixman/pixman-arm-neon-asm.S b/pixman/pixman/pixman-arm-neon-asm.S
index 4f96174d9..47a4e5f60 100644
--- a/pixman/pixman/pixman-arm-neon-asm.S
+++ b/pixman/pixman/pixman-arm-neon-asm.S
@@ -47,6 +47,7 @@
     .eabi_attribute 12, 0 /* suppress Tag_Advanced_SIMD_arch */

     .arm

     .altmacro

+    .p2align 2

 

 #include "pixman-arm-neon-asm.h"

 

diff --git a/pixman/pixman/pixman-arm-simd-asm.S b/pixman/pixman/pixman-arm-simd-asm.S
index e00836b6c..8fe1b5038 100644
--- a/pixman/pixman/pixman-arm-simd-asm.S
+++ b/pixman/pixman/pixman-arm-simd-asm.S
@@ -1,438 +1,439 @@
-/*

- * Copyright © 2008 Mozilla Corporation

- * Copyright © 2010 Nokia Corporation

- *

- * Permission to use, copy, modify, distribute, and sell this software and its

- * documentation for any purpose is hereby granted without fee, provided that

- * the above copyright notice appear in all copies and that both that

- * copyright notice and this permission notice appear in supporting

- * documentation, and that the name of Mozilla Corporation not be used in

- * advertising or publicity pertaining to distribution of the software without

- * specific, written prior permission.  Mozilla Corporation makes no

- * representations about the suitability of this software for any purpose.  It

- * is provided "as is" without express or implied warranty.

- *

- * THE COPYRIGHT HOLDERS DISCLAIM ALL WARRANTIES WITH REGARD TO THIS

- * SOFTWARE, INCLUDING ALL IMPLIED WARRANTIES OF MERCHANTABILITY AND

- * FITNESS, IN NO EVENT SHALL THE COPYRIGHT HOLDERS BE LIABLE FOR ANY

- * SPECIAL, INDIRECT OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES

- * WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN

- * AN ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING

- * OUT OF OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS

- * SOFTWARE.

- *

- * Author:  Jeff Muizelaar (jeff@infidigm.net)

- *

- */

-

-/* Prevent the stack from becoming executable */

-#if defined(__linux__) && defined(__ELF__)

-.section .note.GNU-stack,"",%progbits

-#endif

-

-	.text

-	.arch armv6

-	.object_arch armv4

-	.arm

-	.altmacro

-

-/* Supplementary macro for setting function attributes */

-.macro pixman_asm_function fname

-	.func fname

-	.global fname

-#ifdef __ELF__

-	.hidden fname

-	.type fname, %function

-#endif

-fname:

-.endm

-

-/*

- * The code below was generated by gcc 4.3.4 from the commented out

- * functions in 'pixman-arm-simd.c' file with the following optimization

- * options: "-O3 -mcpu=arm1136jf-s -fomit-frame-pointer"

- *

- * TODO: replace gcc generated code with hand tuned versions because

- * the code quality is not very good, introduce symbolic register

- * aliases for better readability and maintainability.

- */

-

-pixman_asm_function pixman_composite_add_8_8_asm_armv6

-	push	{r4, r5, r6, r7, r8, r9, r10, r11}

-	mov	r10, r1

-	sub	sp, sp, #4

-	subs	r10, r10, #1

-	mov	r11, r0

-	mov	r8, r2

-	str	r3, [sp]

-	ldr	r7, [sp, #36]

-	bcc	0f

-6:	cmp	r11, #0

-	beq	1f

-	orr	r3, r8, r7

-	tst	r3, #3

-	beq	2f

-	mov	r1, r8

-	mov	r0, r7

-	mov	r12, r11

-	b	3f

-5:	tst	r3, #3

-	beq	4f

-3:	ldrb	r2, [r0], #1

-	subs	r12, r12, #1

-	ldrb	r3, [r1]

-	uqadd8	r3, r2, r3

-	strb	r3, [r1], #1

-	orr	r3, r1, r0

-	bne	5b

-1:	ldr	r3, [sp]

-	add	r8, r8, r3

-	ldr	r3, [sp, #40]

-	add	r7, r7, r3

-10:	subs	r10, r10, #1

-	bcs	6b

-0:	add	sp, sp, #4

-	pop	{r4, r5, r6, r7, r8, r9, r10, r11}

-	bx	lr

-2:	mov	r12, r11

-	mov	r1, r8

-	mov	r0, r7

-4:	cmp	r12, #3

-	subgt	r6, r12, #4

-	movgt	r9, r12

-	lsrgt	r5, r6, #2

-	addgt	r3, r5, #1

-	movgt	r12, #0

-	lslgt	r4, r3, #2

-	ble	7f

-8:	ldr	r3, [r0, r12]

-	ldr	r2, [r1, r12]

-	uqadd8	r3, r3, r2

-	str	r3, [r1, r12]

-	add	r12, r12, #4

-	cmp	r12, r4

-	bne	8b

-	sub	r3, r9, #4

-	bic	r3, r3, #3

-	add	r3, r3, #4

-	subs	r12, r6, r5, lsl #2

-	add	r1, r1, r3

-	add	r0, r0, r3

-	beq	1b

-7:	mov	r4, #0

-9:	ldrb	r3, [r1, r4]

-	ldrb	r2, [r0, r4]

-	uqadd8	r3, r2, r3

-	strb	r3, [r1, r4]

-	add	r4, r4, #1

-	cmp	r4, r12

-	bne	9b

-	ldr	r3, [sp]

-	add	r8, r8, r3

-	ldr	r3, [sp, #40]

-	add	r7, r7, r3

-	b	10b

-.endfunc

-

-pixman_asm_function pixman_composite_over_8888_8888_asm_armv6

-	push	{r4, r5, r6, r7, r8, r9, r10, r11}

-	sub	sp, sp, #20

-	cmp	r1, #0

-	mov	r12, r2

-	str	r1, [sp, #12]

-	str	r0, [sp, #16]

-	ldr	r2, [sp, #52]

-	beq	0f

-	lsl	r3, r3, #2

-	str	r3, [sp]

-	ldr	r3, [sp, #56]

-	mov	r10, #0

-	lsl	r3, r3, #2

-	str	r3, [sp, #8]

-	mov	r11, r3

-	b	1f

-6:	ldr	r11, [sp, #8]

-1:	ldr	r9, [sp]

-	mov	r0, r12

-	add	r12, r12, r9

-	mov	r1, r2

-	str	r12, [sp, #4]

-	add	r2, r2, r11

-	ldr	r12, [sp, #16]

-	ldr	r3, =0x00800080

-	ldr	r9, =0xff00ff00

-	mov	r11, #255

-	cmp	r12, #0

-	beq	4f

-5:	ldr	r5, [r1], #4

-	ldr	r4, [r0]

-	sub	r8, r11, r5, lsr #24

-	uxtb16	r6, r4

-	uxtb16	r7, r4, ror #8

-	mla	r6, r6, r8, r3

-	mla	r7, r7, r8, r3

-	uxtab16	r6, r6, r6, ror #8

-	uxtab16	r7, r7, r7, ror #8

-	and	r7, r7, r9

-	uxtab16	r6, r7, r6, ror #8

-	uqadd8	r5, r6, r5

-	str	r5, [r0], #4

-	subs	r12, r12, #1

-	bne	5b

-4:	ldr	r3, [sp, #12]

-	add	r10, r10, #1

-	cmp	r10, r3

-	ldr	r12, [sp, #4]

-	bne	6b

-0:	add	sp, sp, #20

-	pop	{r4, r5, r6, r7, r8, r9, r10, r11}

-	bx	lr

-.endfunc

-

-pixman_asm_function pixman_composite_over_8888_n_8888_asm_armv6

-	push	{r4, r5, r6, r7, r8, r9, r10, r11}

-	sub	sp, sp, #28

-	cmp	r1, #0

-	str	r1, [sp, #12]

-	ldrb	r1, [sp, #71]

-	mov	r12, r2

-	str	r0, [sp, #16]

-	ldr	r2, [sp, #60]

-	str	r1, [sp, #24]

-	beq	0f

-	lsl	r3, r3, #2

-	str	r3, [sp, #20]

-	ldr	r3, [sp, #64]

-	mov	r10, #0

-	lsl	r3, r3, #2

-	str	r3, [sp, #8]

-	mov	r11, r3

-	b	1f

-5:	ldr	r11, [sp, #8]

-1:	ldr	r4, [sp, #20]

-	mov	r0, r12

-	mov	r1, r2

-	add	r12, r12, r4

-	add	r2, r2, r11

-	str	r12, [sp]

-	str	r2, [sp, #4]

-	ldr	r12, [sp, #16]

-	ldr	r2, =0x00800080

-	ldr	r3, [sp, #24]

-	mov	r11, #255

-	cmp	r12, #0

-	beq	3f

-4:	ldr	r5, [r1], #4

-	ldr	r4, [r0]

-	uxtb16	r6, r5

-	uxtb16	r7, r5, ror #8

-	mla	r6, r6, r3, r2

-	mla	r7, r7, r3, r2

-	uxtab16	r6, r6, r6, ror #8

-	uxtab16	r7, r7, r7, ror #8

-	uxtb16	r6, r6, ror #8

-	uxtb16	r7, r7, ror #8

-	orr	r5, r6, r7, lsl #8

-	uxtb16	r6, r4

-	uxtb16	r7, r4, ror #8

-	sub	r8, r11, r5, lsr #24

-	mla	r6, r6, r8, r2

-	mla	r7, r7, r8, r2

-	uxtab16	r6, r6, r6, ror #8

-	uxtab16	r7, r7, r7, ror #8

-	uxtb16	r6, r6, ror #8

-	uxtb16	r7, r7, ror #8

-	orr	r6, r6, r7, lsl #8

-	uqadd8	r5, r6, r5

-	str	r5, [r0], #4

-	subs	r12, r12, #1

-	bne	4b

-3:	ldr	r1, [sp, #12]

-	add	r10, r10, #1

-	cmp	r10, r1

-	ldr	r12, [sp]

-	ldr	r2, [sp, #4]

-	bne	5b

-0:	add	sp, sp, #28

-	pop	{r4, r5, r6, r7, r8, r9, r10, r11}

-	bx	lr

-.endfunc

-

-pixman_asm_function pixman_composite_over_n_8_8888_asm_armv6

-	push	{r4, r5, r6, r7, r8, r9, r10, r11}

-	sub	sp, sp, #28

-	cmp	r1, #0

-	ldr	r9, [sp, #60]

-	str	r1, [sp, #12]

-	bic	r1, r9, #-16777216

-	str	r1, [sp, #20]

-	mov	r12, r2

-	lsr	r1, r9, #8

-	ldr	r2, [sp, #20]

-	bic	r1, r1, #-16777216

-	bic	r2, r2, #65280

-	bic	r1, r1, #65280

-	str	r2, [sp, #20]

-	str	r0, [sp, #16]

-	str	r1, [sp, #4]

-	ldr	r2, [sp, #68]

-	beq	0f

-	lsl	r3, r3, #2

-	str	r3, [sp, #24]

-	mov	r0, #0

-	b	1f

-5:	ldr	r3, [sp, #24]

-1:	ldr	r4, [sp, #72]

-	mov	r10, r12

-	mov	r1, r2

-	add	r12, r12, r3

-	add	r2, r2, r4

-	str	r12, [sp, #8]

-	str	r2, [sp]

-	ldr	r12, [sp, #16]

-	ldr	r11, =0x00800080

-	ldr	r2, [sp, #4]

-	ldr	r3, [sp, #20]

-	cmp	r12, #0

-	beq	3f

-4:	ldrb	r5, [r1], #1

-	ldr	r4, [r10]

-	mla	r6, r3, r5, r11

-	mla	r7, r2, r5, r11

-	uxtab16	r6, r6, r6, ror #8

-	uxtab16	r7, r7, r7, ror #8

-	uxtb16	r6, r6, ror #8

-	uxtb16	r7, r7, ror #8

-	orr	r5, r6, r7, lsl #8

-	uxtb16	r6, r4

-	uxtb16	r7, r4, ror #8

-	mvn	r8, r5

-	lsr	r8, r8, #24

-	mla	r6, r6, r8, r11

-	mla	r7, r7, r8, r11

-	uxtab16	r6, r6, r6, ror #8

-	uxtab16	r7, r7, r7, ror #8

-	uxtb16	r6, r6, ror #8

-	uxtb16	r7, r7, ror #8

-	orr	r6, r6, r7, lsl #8

-	uqadd8	r5, r6, r5

-	str	r5, [r10], #4

-	subs	r12, r12, #1

-	bne	4b

-3:	ldr	r4, [sp, #12]

-	add	r0, r0, #1

-	cmp	r0, r4

-	ldr	r12, [sp, #8]

-	ldr	r2, [sp]

-	bne	5b

-0:	add	sp, sp, #28

-	pop	{r4, r5, r6, r7, r8, r9, r10, r11}

-	bx	lr

-.endfunc

-

-/*

- * Note: This code is only using armv5te instructions (not even armv6),

- *       but is scheduled for ARM Cortex-A8 pipeline. So it might need to

- *       be split into a few variants, tuned for each microarchitecture.

- *

- * TODO: In order to get good performance on ARM9/ARM11 cores (which don't

- * have efficient write combining), it needs to be changed to use 16-byte

- * aligned writes using STM instruction.

- *

- * Nearest scanline scaler macro template uses the following arguments:

- *  fname                     - name of the function to generate

- *  bpp_shift                 - (1 << bpp_shift) is the size of pixel in bytes

- *  t                         - type suffix for LDR/STR instructions

- *  prefetch_distance         - prefetch in the source image by that many

- *                              pixels ahead

- *  prefetch_braking_distance - stop prefetching when that many pixels are

- *                              remaining before the end of scanline

- */

-

-.macro generate_nearest_scanline_func fname, bpp_shift, t,      \

-                                      prefetch_distance,        \

-                                      prefetch_braking_distance

-

-pixman_asm_function fname

-	W	.req	r0

-	DST	.req	r1

-	SRC	.req	r2

-	VX	.req	r3

-	UNIT_X	.req	ip

-	TMP1	.req	r4

-	TMP2	.req	r5

-	VXMASK	.req	r6

-	PF_OFFS	.req	r7

-

-	ldr	UNIT_X, [sp]

-	push	{r4, r5, r6, r7}

-	mvn	VXMASK, #((1 << bpp_shift) - 1)

-

-	/* define helper macro */

-	.macro	scale_2_pixels

-		ldr&t	TMP1, [SRC, TMP1]

-		and	TMP2, VXMASK, VX, lsr #(16 - bpp_shift)

-		add	VX, VX, UNIT_X

-		str&t	TMP1, [DST], #(1 << bpp_shift)

-

-		ldr&t	TMP2, [SRC, TMP2]

-		and	TMP1, VXMASK, VX, lsr #(16 - bpp_shift)

-		add	VX, VX, UNIT_X

-		str&t	TMP2, [DST], #(1 << bpp_shift)

-	.endm

-

-	/* now do the scaling */

-	and	TMP1, VXMASK, VX, lsr #(16 - bpp_shift)

-	add	VX, VX, UNIT_X

-	subs	W, W, #(8 + prefetch_braking_distance)

-	blt	2f

-	/* calculate prefetch offset */

-	mov	PF_OFFS, #prefetch_distance

-	mla	PF_OFFS, UNIT_X, PF_OFFS, VX

-1:	/* main loop, process 8 pixels per iteration with prefetch */

-	subs	W, W, #8

-	add	PF_OFFS, UNIT_X, lsl #3

-	scale_2_pixels

-	scale_2_pixels

-	scale_2_pixels

-	scale_2_pixels

-	pld	[SRC, PF_OFFS, lsr #(16 - bpp_shift)]

-	bge	1b

-2:

-	subs	W, W, #(4 - 8 - prefetch_braking_distance)

-	blt	2f

-1:	/* process the remaining pixels */

-	scale_2_pixels

-	scale_2_pixels

-	subs	W, W, #4

-	bge	1b

-2:

-	tst	W, #2

-	beq	2f

-	scale_2_pixels

-2:

-	tst	W, #1

-	ldrne&t	TMP1, [SRC, TMP1]

-	strne&t	TMP1, [DST]

-	/* cleanup helper macro */

-	.purgem	scale_2_pixels

-	.unreq	DST

-	.unreq	SRC

-	.unreq	W

-	.unreq	VX

-	.unreq	UNIT_X

-	.unreq	TMP1

-	.unreq	TMP2

-	.unreq	VXMASK

-	.unreq	PF_OFFS

-	/* return */

-	pop	{r4, r5, r6, r7}

-	bx	lr

-.endfunc

-.endm

-

-generate_nearest_scanline_func \

-    pixman_scaled_nearest_scanline_0565_0565_SRC_asm_armv6, 1, h, 80, 32

-

-generate_nearest_scanline_func \

-    pixman_scaled_nearest_scanline_8888_8888_SRC_asm_armv6, 2,  , 48, 32

+/*
+ * Copyright © 2008 Mozilla Corporation
+ * Copyright © 2010 Nokia Corporation
+ *
+ * Permission to use, copy, modify, distribute, and sell this software and its
+ * documentation for any purpose is hereby granted without fee, provided that
+ * the above copyright notice appear in all copies and that both that
+ * copyright notice and this permission notice appear in supporting
+ * documentation, and that the name of Mozilla Corporation not be used in
+ * advertising or publicity pertaining to distribution of the software without
+ * specific, written prior permission.  Mozilla Corporation makes no
+ * representations about the suitability of this software for any purpose.  It
+ * is provided "as is" without express or implied warranty.
+ *
+ * THE COPYRIGHT HOLDERS DISCLAIM ALL WARRANTIES WITH REGARD TO THIS
+ * SOFTWARE, INCLUDING ALL IMPLIED WARRANTIES OF MERCHANTABILITY AND
+ * FITNESS, IN NO EVENT SHALL THE COPYRIGHT HOLDERS BE LIABLE FOR ANY
+ * SPECIAL, INDIRECT OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
+ * WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN
+ * AN ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING
+ * OUT OF OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS
+ * SOFTWARE.
+ *
+ * Author:  Jeff Muizelaar (jeff@infidigm.net)
+ *
+ */
+
+/* Prevent the stack from becoming executable */
+#if defined(__linux__) && defined(__ELF__)
+.section .note.GNU-stack,"",%progbits
+#endif
+
+	.text
+	.arch armv6
+	.object_arch armv4
+	.arm
+	.altmacro
+	.p2align 2
+
+/* Supplementary macro for setting function attributes */
+.macro pixman_asm_function fname
+	.func fname
+	.global fname
+#ifdef __ELF__
+	.hidden fname
+	.type fname, %function
+#endif
+fname:
+.endm
+
+/*
+ * The code below was generated by gcc 4.3.4 from the commented out
+ * functions in 'pixman-arm-simd.c' file with the following optimization
+ * options: "-O3 -mcpu=arm1136jf-s -fomit-frame-pointer"
+ *
+ * TODO: replace gcc generated code with hand tuned versions because
+ * the code quality is not very good, introduce symbolic register
+ * aliases for better readability and maintainability.
+ */
+
+pixman_asm_function pixman_composite_add_8_8_asm_armv6
+	push	{r4, r5, r6, r7, r8, r9, r10, r11}
+	mov	r10, r1
+	sub	sp, sp, #4
+	subs	r10, r10, #1
+	mov	r11, r0
+	mov	r8, r2
+	str	r3, [sp]
+	ldr	r7, [sp, #36]
+	bcc	0f
+6:	cmp	r11, #0
+	beq	1f
+	orr	r3, r8, r7
+	tst	r3, #3
+	beq	2f
+	mov	r1, r8
+	mov	r0, r7
+	mov	r12, r11
+	b	3f
+5:	tst	r3, #3
+	beq	4f
+3:	ldrb	r2, [r0], #1
+	subs	r12, r12, #1
+	ldrb	r3, [r1]
+	uqadd8	r3, r2, r3
+	strb	r3, [r1], #1
+	orr	r3, r1, r0
+	bne	5b
+1:	ldr	r3, [sp]
+	add	r8, r8, r3
+	ldr	r3, [sp, #40]
+	add	r7, r7, r3
+10:	subs	r10, r10, #1
+	bcs	6b
+0:	add	sp, sp, #4
+	pop	{r4, r5, r6, r7, r8, r9, r10, r11}
+	bx	lr
+2:	mov	r12, r11
+	mov	r1, r8
+	mov	r0, r7
+4:	cmp	r12, #3
+	subgt	r6, r12, #4
+	movgt	r9, r12
+	lsrgt	r5, r6, #2
+	addgt	r3, r5, #1
+	movgt	r12, #0
+	lslgt	r4, r3, #2
+	ble	7f
+8:	ldr	r3, [r0, r12]
+	ldr	r2, [r1, r12]
+	uqadd8	r3, r3, r2
+	str	r3, [r1, r12]
+	add	r12, r12, #4
+	cmp	r12, r4
+	bne	8b
+	sub	r3, r9, #4
+	bic	r3, r3, #3
+	add	r3, r3, #4
+	subs	r12, r6, r5, lsl #2
+	add	r1, r1, r3
+	add	r0, r0, r3
+	beq	1b
+7:	mov	r4, #0
+9:	ldrb	r3, [r1, r4]
+	ldrb	r2, [r0, r4]
+	uqadd8	r3, r2, r3
+	strb	r3, [r1, r4]
+	add	r4, r4, #1
+	cmp	r4, r12
+	bne	9b
+	ldr	r3, [sp]
+	add	r8, r8, r3
+	ldr	r3, [sp, #40]
+	add	r7, r7, r3
+	b	10b
+.endfunc
+
+pixman_asm_function pixman_composite_over_8888_8888_asm_armv6
+	push	{r4, r5, r6, r7, r8, r9, r10, r11}
+	sub	sp, sp, #20
+	cmp	r1, #0
+	mov	r12, r2
+	str	r1, [sp, #12]
+	str	r0, [sp, #16]
+	ldr	r2, [sp, #52]
+	beq	0f
+	lsl	r3, r3, #2
+	str	r3, [sp]
+	ldr	r3, [sp, #56]
+	mov	r10, #0
+	lsl	r3, r3, #2
+	str	r3, [sp, #8]
+	mov	r11, r3
+	b	1f
+6:	ldr	r11, [sp, #8]
+1:	ldr	r9, [sp]
+	mov	r0, r12
+	add	r12, r12, r9
+	mov	r1, r2
+	str	r12, [sp, #4]
+	add	r2, r2, r11
+	ldr	r12, [sp, #16]
+	ldr	r3, =0x00800080
+	ldr	r9, =0xff00ff00
+	mov	r11, #255
+	cmp	r12, #0
+	beq	4f
+5:	ldr	r5, [r1], #4
+	ldr	r4, [r0]
+	sub	r8, r11, r5, lsr #24
+	uxtb16	r6, r4
+	uxtb16	r7, r4, ror #8
+	mla	r6, r6, r8, r3
+	mla	r7, r7, r8, r3
+	uxtab16	r6, r6, r6, ror #8
+	uxtab16	r7, r7, r7, ror #8
+	and	r7, r7, r9
+	uxtab16	r6, r7, r6, ror #8
+	uqadd8	r5, r6, r5
+	str	r5, [r0], #4
+	subs	r12, r12, #1
+	bne	5b
+4:	ldr	r3, [sp, #12]
+	add	r10, r10, #1
+	cmp	r10, r3
+	ldr	r12, [sp, #4]
+	bne	6b
+0:	add	sp, sp, #20
+	pop	{r4, r5, r6, r7, r8, r9, r10, r11}
+	bx	lr
+.endfunc
+
+pixman_asm_function pixman_composite_over_8888_n_8888_asm_armv6
+	push	{r4, r5, r6, r7, r8, r9, r10, r11}
+	sub	sp, sp, #28
+	cmp	r1, #0
+	str	r1, [sp, #12]
+	ldrb	r1, [sp, #71]
+	mov	r12, r2
+	str	r0, [sp, #16]
+	ldr	r2, [sp, #60]
+	str	r1, [sp, #24]
+	beq	0f
+	lsl	r3, r3, #2
+	str	r3, [sp, #20]
+	ldr	r3, [sp, #64]
+	mov	r10, #0
+	lsl	r3, r3, #2
+	str	r3, [sp, #8]
+	mov	r11, r3
+	b	1f
+5:	ldr	r11, [sp, #8]
+1:	ldr	r4, [sp, #20]
+	mov	r0, r12
+	mov	r1, r2
+	add	r12, r12, r4
+	add	r2, r2, r11
+	str	r12, [sp]
+	str	r2, [sp, #4]
+	ldr	r12, [sp, #16]
+	ldr	r2, =0x00800080
+	ldr	r3, [sp, #24]
+	mov	r11, #255
+	cmp	r12, #0
+	beq	3f
+4:	ldr	r5, [r1], #4
+	ldr	r4, [r0]
+	uxtb16	r6, r5
+	uxtb16	r7, r5, ror #8
+	mla	r6, r6, r3, r2
+	mla	r7, r7, r3, r2
+	uxtab16	r6, r6, r6, ror #8
+	uxtab16	r7, r7, r7, ror #8
+	uxtb16	r6, r6, ror #8
+	uxtb16	r7, r7, ror #8
+	orr	r5, r6, r7, lsl #8
+	uxtb16	r6, r4
+	uxtb16	r7, r4, ror #8
+	sub	r8, r11, r5, lsr #24
+	mla	r6, r6, r8, r2
+	mla	r7, r7, r8, r2
+	uxtab16	r6, r6, r6, ror #8
+	uxtab16	r7, r7, r7, ror #8
+	uxtb16	r6, r6, ror #8
+	uxtb16	r7, r7, ror #8
+	orr	r6, r6, r7, lsl #8
+	uqadd8	r5, r6, r5
+	str	r5, [r0], #4
+	subs	r12, r12, #1
+	bne	4b
+3:	ldr	r1, [sp, #12]
+	add	r10, r10, #1
+	cmp	r10, r1
+	ldr	r12, [sp]
+	ldr	r2, [sp, #4]
+	bne	5b
+0:	add	sp, sp, #28
+	pop	{r4, r5, r6, r7, r8, r9, r10, r11}
+	bx	lr
+.endfunc
+
+pixman_asm_function pixman_composite_over_n_8_8888_asm_armv6
+	push	{r4, r5, r6, r7, r8, r9, r10, r11}
+	sub	sp, sp, #28
+	cmp	r1, #0
+	ldr	r9, [sp, #60]
+	str	r1, [sp, #12]
+	bic	r1, r9, #-16777216
+	str	r1, [sp, #20]
+	mov	r12, r2
+	lsr	r1, r9, #8
+	ldr	r2, [sp, #20]
+	bic	r1, r1, #-16777216
+	bic	r2, r2, #65280
+	bic	r1, r1, #65280
+	str	r2, [sp, #20]
+	str	r0, [sp, #16]
+	str	r1, [sp, #4]
+	ldr	r2, [sp, #68]
+	beq	0f
+	lsl	r3, r3, #2
+	str	r3, [sp, #24]
+	mov	r0, #0
+	b	1f
+5:	ldr	r3, [sp, #24]
+1:	ldr	r4, [sp, #72]
+	mov	r10, r12
+	mov	r1, r2
+	add	r12, r12, r3
+	add	r2, r2, r4
+	str	r12, [sp, #8]
+	str	r2, [sp]
+	ldr	r12, [sp, #16]
+	ldr	r11, =0x00800080
+	ldr	r2, [sp, #4]
+	ldr	r3, [sp, #20]
+	cmp	r12, #0
+	beq	3f
+4:	ldrb	r5, [r1], #1
+	ldr	r4, [r10]
+	mla	r6, r3, r5, r11
+	mla	r7, r2, r5, r11
+	uxtab16	r6, r6, r6, ror #8
+	uxtab16	r7, r7, r7, ror #8
+	uxtb16	r6, r6, ror #8
+	uxtb16	r7, r7, ror #8
+	orr	r5, r6, r7, lsl #8
+	uxtb16	r6, r4
+	uxtb16	r7, r4, ror #8
+	mvn	r8, r5
+	lsr	r8, r8, #24
+	mla	r6, r6, r8, r11
+	mla	r7, r7, r8, r11
+	uxtab16	r6, r6, r6, ror #8
+	uxtab16	r7, r7, r7, ror #8
+	uxtb16	r6, r6, ror #8
+	uxtb16	r7, r7, ror #8
+	orr	r6, r6, r7, lsl #8
+	uqadd8	r5, r6, r5
+	str	r5, [r10], #4
+	subs	r12, r12, #1
+	bne	4b
+3:	ldr	r4, [sp, #12]
+	add	r0, r0, #1
+	cmp	r0, r4
+	ldr	r12, [sp, #8]
+	ldr	r2, [sp]
+	bne	5b
+0:	add	sp, sp, #28
+	pop	{r4, r5, r6, r7, r8, r9, r10, r11}
+	bx	lr
+.endfunc
+
+/*
+ * Note: This code is only using armv5te instructions (not even armv6),
+ *       but is scheduled for ARM Cortex-A8 pipeline. So it might need to
+ *       be split into a few variants, tuned for each microarchitecture.
+ *
+ * TODO: In order to get good performance on ARM9/ARM11 cores (which don't
+ * have efficient write combining), it needs to be changed to use 16-byte
+ * aligned writes using STM instruction.
+ *
+ * Nearest scanline scaler macro template uses the following arguments:
+ *  fname                     - name of the function to generate
+ *  bpp_shift                 - (1 << bpp_shift) is the size of pixel in bytes
+ *  t                         - type suffix for LDR/STR instructions
+ *  prefetch_distance         - prefetch in the source image by that many
+ *                              pixels ahead
+ *  prefetch_braking_distance - stop prefetching when that many pixels are
+ *                              remaining before the end of scanline
+ */
+
+.macro generate_nearest_scanline_func fname, bpp_shift, t,      \
+                                      prefetch_distance,        \
+                                      prefetch_braking_distance
+
+pixman_asm_function fname
+	W	.req	r0
+	DST	.req	r1
+	SRC	.req	r2
+	VX	.req	r3
+	UNIT_X	.req	ip
+	TMP1	.req	r4
+	TMP2	.req	r5
+	VXMASK	.req	r6
+	PF_OFFS	.req	r7
+
+	ldr	UNIT_X, [sp]
+	push	{r4, r5, r6, r7}
+	mvn	VXMASK, #((1 << bpp_shift) - 1)
+
+	/* define helper macro */
+	.macro	scale_2_pixels
+		ldr&t	TMP1, [SRC, TMP1]
+		and	TMP2, VXMASK, VX, lsr #(16 - bpp_shift)
+		add	VX, VX, UNIT_X
+		str&t	TMP1, [DST], #(1 << bpp_shift)
+
+		ldr&t	TMP2, [SRC, TMP2]
+		and	TMP1, VXMASK, VX, lsr #(16 - bpp_shift)
+		add	VX, VX, UNIT_X
+		str&t	TMP2, [DST], #(1 << bpp_shift)
+	.endm
+
+	/* now do the scaling */
+	and	TMP1, VXMASK, VX, lsr #(16 - bpp_shift)
+	add	VX, VX, UNIT_X
+	subs	W, W, #(8 + prefetch_braking_distance)
+	blt	2f
+	/* calculate prefetch offset */
+	mov	PF_OFFS, #prefetch_distance
+	mla	PF_OFFS, UNIT_X, PF_OFFS, VX
+1:	/* main loop, process 8 pixels per iteration with prefetch */
+	subs	W, W, #8
+	add	PF_OFFS, UNIT_X, lsl #3
+	scale_2_pixels
+	scale_2_pixels
+	scale_2_pixels
+	scale_2_pixels
+	pld	[SRC, PF_OFFS, lsr #(16 - bpp_shift)]
+	bge	1b
+2:
+	subs	W, W, #(4 - 8 - prefetch_braking_distance)
+	blt	2f
+1:	/* process the remaining pixels */
+	scale_2_pixels
+	scale_2_pixels
+	subs	W, W, #4
+	bge	1b
+2:
+	tst	W, #2
+	beq	2f
+	scale_2_pixels
+2:
+	tst	W, #1
+	ldrne&t	TMP1, [SRC, TMP1]
+	strne&t	TMP1, [DST]
+	/* cleanup helper macro */
+	.purgem	scale_2_pixels
+	.unreq	DST
+	.unreq	SRC
+	.unreq	W
+	.unreq	VX
+	.unreq	UNIT_X
+	.unreq	TMP1
+	.unreq	TMP2
+	.unreq	VXMASK
+	.unreq	PF_OFFS
+	/* return */
+	pop	{r4, r5, r6, r7}
+	bx	lr
+.endfunc
+.endm
+
+generate_nearest_scanline_func \
+    pixman_scaled_nearest_scanline_0565_0565_SRC_asm_armv6, 1, h, 80, 32
+
+generate_nearest_scanline_func \
+    pixman_scaled_nearest_scanline_8888_8888_SRC_asm_armv6, 2,  , 48, 32